© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 10065
    Prev
    Next
    INDEX
    Explanations

    phrases indicating rankings or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nosa
    -0.43
    ativna
    -0.40
    WriteTagHelper
    -0.39
    üyada
    -0.36
    ucoup
    -0.35
     Gute
    -0.35
    usable
    -0.34
    irmer
    -0.34
    gages
    -0.34
    有多
    -0.34
    POSITIVE LOGITS
     ten
    0.51
     seven
    0.50
     eight
    0.49
    fromnode
    0.48
     fifteen
    0.47
    SpringRunner
    0.46
     eleven
    0.45
     nine
    0.45
    脚注の使い方
    0.45
     nineteen
    0.43
    Activations Density 0.355%

    No Known Activations